2026-09-06T12:40:15.853505Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 4, column_partitions: 92, inner_partitions: 4, result_row_partitions: 4, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:40:16.405886Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 4, column_partitions: 24, inner_partitions: 15, result_row_partitions: 15, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Standard, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:40:16.954819Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=259590 estimated_exchange_cycles=123960 exchange_row_bytes=27236 peak_standard_bytes=169572 peak_interleaved_bytes=60416 peak_total_bytes=229988 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:40:16.962373Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=1419 success=true
2026-09-06T12:40:20.811330Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=192930 estimated_exchange_cycles=70152
2026-09-06T12:40:20.955919Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: eliminated finite GEMM padding clears using load-time SRAM initialization removed=72
2026-09-06T12:40:20.959781Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=3997 success=true
2026-09-06T12:40:20.959828Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=4
2026-09-06T12:40:20.960095Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true
2026-09-06T12:40:20.961702Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=1 success=true
2026-09-06T12:40:20.962086Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=0 success=true
2026-09-06T12:40:20.965428Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true
2026-09-06T12:40:21.562780Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="plan_exchange_storage"}: package build phase finished phase="plan_exchange_storage" elapsed_ms=597 success=true
2026-09-06T12:40:22.313911Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=1 transfers=15064 maximum_identical_destinations=1
2026-09-06T12:40:22.313966Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=1 initial_horizon=4517 selected_horizon=4517 endpoint_lower_bound=3408 lower_bound_gap=1109 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:22.325847Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=1 tile=799 row_words=73 horizon=4517
2026-09-06T12:40:25.946565Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=2 transfers=5562 maximum_identical_destinations=1
2026-09-06T12:40:25.946619Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=2 initial_horizon=38508 selected_horizon=38508 endpoint_lower_bound=33408 lower_bound_gap=5100 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:25.986141Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=2 tile=691 row_words=238 horizon=38508
2026-09-06T12:40:33.803636Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=3 transfers=63720 maximum_identical_destinations=1
2026-09-06T12:40:33.803690Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=3 initial_horizon=8171 selected_horizon=8171 endpoint_lower_bound=4704 lower_bound_gap=3467 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:33.903013Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=3 tile=983 row_words=297 horizon=8171
2026-09-06T12:40:33.956242Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: package build phase finished phase="lower_exchanges_provisional" elapsed_ms=12393 success=true
2026-09-06T12:40:34.858745Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="size_tile_code"}: package build phase finished phase="size_tile_code" elapsed_ms=4 success=true
2026-09-06T12:40:34.858779Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=2316 host_code_bytes=2416 generated_code_bytes=1544 code_address=319456 standard_ranges=[(409600, 524288)]
2026-09-06T12:40:35.197577Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="place_storage"}: package build phase finished phase="place_storage" elapsed_ms=338 success=true
2026-09-06T12:40:35.212967Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T12:40:35.986651Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=1 transfers=15064 maximum_identical_destinations=1
2026-09-06T12:40:35.986697Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=1 initial_horizon=4517 selected_horizon=4517 endpoint_lower_bound=3408 lower_bound_gap=1109 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:36.019456Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=1 tile=799 row_words=73 horizon=4517
2026-09-06T12:40:40.707790Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=2 transfers=5562 maximum_identical_destinations=1
2026-09-06T12:40:40.707844Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=2 initial_horizon=38508 selected_horizon=38508 endpoint_lower_bound=33408 lower_bound_gap=5100 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:40.748610Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=2 tile=691 row_words=238 horizon=38508
2026-09-06T12:40:49.304463Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=3 transfers=63720 maximum_identical_destinations=1
2026-09-06T12:40:49.304515Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=3 initial_horizon=8171 selected_horizon=8171 endpoint_lower_bound=4704 lower_bound_gap=3467 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:49.394698Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=3 tile=983 row_words=297 horizon=8171
2026-09-06T12:40:49.429655Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: package build phase finished phase="lower_exchanges" elapsed_ms=14232 success=true
2026-09-06T12:40:51.757256Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T12:40:51.885320Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: reused exchange optimization after validating relocated rows phase=1
2026-09-06T12:40:51.896718Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=1 transfers=15064 maximum_identical_destinations=1
2026-09-06T12:40:51.896743Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=1 initial_horizon=4517 selected_horizon=4517 endpoint_lower_bound=3408 lower_bound_gap=1109 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:51.915513Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=1 tile=799 row_words=73 horizon=4517
2026-09-06T12:40:55.892256Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=2 transfers=5562 maximum_identical_destinations=1
2026-09-06T12:40:55.892306Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=2 initial_horizon=36116 selected_horizon=36116 endpoint_lower_bound=33408 lower_bound_gap=2708 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:55.933493Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=2 tile=691 row_words=239 horizon=36116
2026-09-06T12:41:02.477633Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=3 transfers=63720 maximum_identical_destinations=1
2026-09-06T12:41:02.477657Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=3 initial_horizon=8171 selected_horizon=8171 endpoint_lower_bound=4704 lower_bound_gap=3467 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:41:02.521646Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=3 tile=983 row_words=297 horizon=8171
2026-09-06T12:41:02.544419Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=28672 baseline_score=170111729664 score=151709220864 baseline_cycles=58244 candidate_cycles=55852 row_bytes=2308 row_capacity=16320 accepted=true
2026-09-06T12:41:02.553232Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: package build phase finished phase="optimize_exchange_placement" elapsed_ms=13123 success=true
2026-09-06T12:41:02.770625Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="prepare_tile_code"}: package build phase finished phase="prepare_tile_code" elapsed_ms=10 success=true
2026-09-06T12:41:02.780919Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="emit_tile_code"}: package build phase finished phase="emit_tile_code" elapsed_ms=10 success=true
2026-09-06T12:41:02.869056Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="build_tile_images"}: package build phase finished phase="build_tile_images" elapsed_ms=83 success=true
2026-09-06T12:41:02.933574Z  INFO writing application package tiles=1472
2026-09-06T12:41:02.962944Z  INFO application package written
2026-09-06T12:41:02.963432Z  INFO reading application package
2026-09-06T12:41:03.052029Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:41:03.052309Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:41:19.654803Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:41:19.654855Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:41:19.654919Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:41:19.654925Z  INFO initializing IPU device
2026-09-06T12:41:19.663065Z  INFO IPU device initialized
2026-09-06T12:41:19.663082Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:41:19.672131Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:41:19.939223Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:41:22.370512Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:41:22.370537Z  INFO attaching host exchange pages pages=2
2026-09-06T12:41:22.371069Z  INFO host exchange session started
2026-09-06T12:41:22.371151Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:41:22.377905Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-followup/mapping-block-368-92-base/execution.ipuprofile tiles=1472 samples=25788
workload=siglip-mlp-f16-b1-t729-d1152-h4304-n1 benchmark=siglip-mlp-f16 batch=1 tokens=729 rows=729 dimension=1152 hiddenDimension=4304 blocks=1 biases=false activeTiles=1440 executionTiles=1472 inputBytes=154736640 weightBytes=19869696 cycles=187032 minimumTileCycles=174618 deviceMicroseconds=124.688 effectiveGemmTflops=115.954 peakTflops=282.624 efficiencyPercent=41.03 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-followup/mapping-block-368-92-base/model.ipuexe tiles=1472 hardwareTest=PASS